基于神经网络的模拟电路故障诊断的仿真研究  

Simulation Research on Fault Diagnosis of Analog Circuit Based on Neural Network

作　　者：杨焕峥 崔业梅[1,2] 杨国华 杨贝贝[2] YANGHuan-zheng;CUI Ye-mei;YANG Guo-hua;YANG Bei-bei(Jiangsu Research and Development Center ofApplication Technology far Wireless Sensing System,Wuxi Jiangsu 214153;Wuxi Institute of Commerce,Wuxi Jiangsu 214153)

机构地区：[1]江苏省无线传感系统应用工程技术开发中心,江苏无锡214153 [2]无锡商业职业技术学院,江苏无锡214153

出　　处：《长沙航空职业技术学院学报》2020年第4期66-72,共7页Journal of Changsha Aeronautical Vocational and Technical College

基　　金：2020年江苏高校"青蓝工程"资助;2020年江苏省高等学校大学生创新创业训练计划项目(创新训练项目)"一种基于神经网络和LabVIEW的模拟电路故障诊断系统"(编号:202012702015Y)阶段性研究成果。

摘　　要：为了辅助学生进行模拟电路板特定故障的诊断训练,基于人工神经网络模型通过LabVIEW和MATLAB软件联合编程进行仿真研究,利用MATLAB软件工具建立神经网络模型,并使用预先采集的电路板故障样本数据对模型的参数进行训练,利用LabVIEW软件调用已训练好的神经网络模型对输入的待诊断数据进行分析,得出故障类型结果并显示,系统诊断准确率较高,效果较好。In order to assist students in the diagnosis training of analog circuit board specific fault,and based on the artificial neural network model,joint programming and simulation research are carried out by softwares of LABVIEW and MATLAB.The neural network model is established by using MATLAB software tools,and the parameters of the model are trained by using the pre-collected circuit board fault sample data.LABVIEW software was used to call the trained neural network model to analyze the input data to be diagnosed.LABVIEW software is used to call the trained neural network model to analyze the input data to be diagnosed.The fault type was obtained,and the result showed that the system diagnosis accuracy is higher and the effect is better.

关 键 词：神经网络 模拟电路 故障判断 矩阵实验室 虚拟仪器 

分 类 号：TN7[电子电信—电路与系统] TP183[自动化与计算机技术—控制理论与控制工程]